Training update: 1,298/237,619 rows (0.55%) | +50 new @ 2025-10-20 06:01:21

README.md

@@ -13,12 +13,12 @@ base_model: boltuix/bert-micro
 ## 1. Model Details
 
 **Model description**  
-"bert-micro-cybersecurity" is a compact transformer model derived from `boltuix/bert-micro`, adapted for cybersecurity text classification tasks (e.g., threat detection, incident reports, malicious vs benign content).
+"bert-micro-cybersecurity" is a compact transformer model adapted for cybersecurity text classification tasks (e.g., threat detection, incident reports, malicious vs benign content).
 
 - Model type: fine-tuned lightweight BERT variant  
 - Languages: English & Indonesia
 - Finetuned from: `boltuix/bert-micro`
-- Status: **Early version** — trained on **1.86%** of planned data.
+- Status: **Early version** — trained on **0.55%** of planned data.
 
 **Model sources**  
 - Base model: [boltuix/bert-micro](https://huggingface.co/boltuix/bert-micro)
@@ -41,7 +41,7 @@ You can use this model to classify cybersecurity-related text — for example, w
 
 ## 3. Bias, Risks, and Limitations 
 
-Because the model is based on a small subset (1.86%) of planned data, performance is preliminary and may degrade on unseen or specialized domains (industrial control, IoT logs, foreign language).
+Because the model is based on a small subset (0.55%) of planned data, performance is preliminary and may degrade on unseen or specialized domains (industrial control, IoT logs, foreign language).
 
 - Inherits any biases present in the base model (`boltuix/bert-micro`) and in the fine-tuning data — e.g., over-representation of certain threat types, vendor or tooling-specific vocabulary.
 - Should not be used as sole authority for incident decisions; only as an aid to human analysts.
@@ -63,7 +63,7 @@ predicted_class = logits.argmax(dim=-1).item()
 
 ## 5. Training Details
 
-- **Trained records**: 1,260 / 67,618 (1.86%)
+- **Trained records**: 1,298 / 237,619 (0.55%)
 - **Learning rate**: 5e-05
 - **Epochs**: 3
 - **Batch size**: 1

checkpoint-399/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.57.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

checkpoint-399/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5c7b02bb13ebf2905410619055cb013385b4011c032639fe17fcccdebaa0782
+size 17671560

checkpoint-399/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c55b7ea85087a6425483e191a3425e14973a52dd8ba2a0bf258b595d34b290e
+size 35368075

checkpoint-399/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e30ff8827cc04d333a3515bde51c8e701e5b0a041c94195a2ecf5dd4f023f92
+size 14455

checkpoint-399/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d886584f6f9ad818746ccaa9537f161b2526cb5d1b0541cd9be4f626cc43ca6b
+size 1465

checkpoint-399/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-399/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

checkpoint-399/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 399,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.7518796992481203,
+      "grad_norm": 37.094478607177734,
+      "learning_rate": 4e-05,
+      "loss": 4.3381,
+      "step": 100
+    },
+    {
+      "epoch": 1.5037593984962405,
+      "grad_norm": 0.0,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 4.1538,
+      "step": 200
+    },
+    {
+      "epoch": 2.255639097744361,
+      "grad_norm": 12.260258674621582,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 3.6074,
+      "step": 300
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 399,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 544333547520.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-399/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:923e344d96e07850933e9f1da23fb1dd6dd58910ee71a5248d69e14f54590898
+size 5841

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea4e1367fc7a89da294decbd67eaa8eb5a499457cddc489370ba5a0f4153c787
+oid sha256:d5c7b02bb13ebf2905410619055cb013385b4011c032639fe17fcccdebaa0782
 size 17671560

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c57c5de3eaba678d4bafcb1b8d5390e895d371b501b5b1b46356182c51fc0da
+oid sha256:923e344d96e07850933e9f1da23fb1dd6dd58910ee71a5248d69e14f54590898
 size 5841

training_metadata.json

@@ -1,11 +1,11 @@
 {
-  "trained_at": 1760939135.9935098,
-  "trained_at_readable": "2025-10-20 05:45:35",
-  "samples_this_session": 1000,
-  "new_rows_this_session": 1000,
-  "trained_rows_total": 1260,
-  "total_db_rows": 67618,
-  "percentage": 1.863409151409388,
+  "trained_at": 1760940081.235496,
+  "trained_at_readable": "2025-10-20 06:01:21",
+  "samples_this_session": 133,
+  "new_rows_this_session": 50,
+  "trained_rows_total": 1298,
+  "total_db_rows": 237619,
+  "percentage": 0.5462526144794818,
   "final_loss": 0,
   "epochs": 3,
   "learning_rate": 5e-05